SparseCoding

SparseCoding: A sparse coding hierarchy for realtime object recognition in complex scenes

FCT - Vision Laboratory - CINTAL/UAlg, EXPL/EEI-SII/1982/2013

Synopsis

This exploratory project as the main goal to combine two basic ideas:

(1) A kind of Hopfield neural network that is extended by an additional layer of neurons, called cliques, which code learned relations between basic patterns. The introduced redundancy leads to sparse codes and makes the new type of network very robust to incomplete data and noise. It is a form of neuromimetic computing, as a compact and fast model of our brain's neocortex which combines pattern recognition with associative memory.

(2) By building a hierarchy of such networks, translation- and rotation-invariant object recognition can be achieved. At a low level, very primitive and small patterns can be learned and detected, like edge fragments and corners linking edges. One level higher, these primitives are combined into bigger and more complex structures, with less dependency on precise localization. This is repeated until the top layer, where entire objects are coded irrespective of their position in the scene.

See also: link

Publications

  • Martins, Jaime A., Rodrigues, João M.F., du Buf, J.M.H. (2015) Expression-Invariant Face Recognition using a Biological Disparity Energy Model, submitted to Information Sciences (Informatics and Computer Science Intelligent Systems Applications) (link)
  • Saleiro, M., Farrajota, M., Terzic, K., Krishna, S., Rodrigues, J.M.F., du Buf, J.M.H. (2015) Biologically inspired vision for human-robot interaction, In M. Antona and C. Stephanidis (Eds.): Universal Access in Human-Computer Interaction 2015, Part II, LNCS 9176, pp. 505–517. doi: 10.1007/978-3-319-20681-3_48 (link)
  • Martins, Jaime A., Rodrigues, João M.F., du Buf, J.M.H. (2015) Proto-Object Categorisation and Local Gist Vision using Low-Level Spatial Features, BioSystems. doi:10.1016/j.biosystems.2015.07.001 (link)
  • Martins, Jaime A., Rodrigues, João M.F., du Buf, J.M.H. (2015) Luminance, Colour, Viewpoint and Border Enhanced Disparity Energy Model, PLoS ONE 10(6): e0129908. doi:10.1371/journal.pone.0129908 (link)
  • Farrajota, M., Rodrigues, J.M.F., du Buf, J.M.H. (2015) Bio-Inspired Pedestrian Detection and Tracking, In Proc. 3rd Int. Conf. on Advances in Bio-Informatics, Bio-Technology and Environmental Engineering, Birminghan, UK, 26-27 May, pp. 28-33. ISBN: 978-1-63248-060-6. doi: 10.15224/978-1-63248-060-6-07 (link)
  • Saleiro, M., Terzic, K., Lobato, D., Rodrigues, J.M.F., du Buf, J.M.H. (2014) Biologically inspired vision for indoor robot navigation, In Campilho, Aurélio, Kamel, Mohamed (Eds.): Image Analysis and Recognition, Part II, vol. 8815, pp 469-477, Springer International Publishing. doi: 10.1007/978-3-319-11755-3_52. (link)
  • Rodrigues, J.M.F., Terzic, K., Lam, R., du Buf, J.M.H. (2014) Face and Object Recognition Using Biological Features and few Views, Chapter 4 in Contemporary Advancements in Information Technology Development in Dynamic Environments, Mehdi Khosrow-Pour (ed.), IGI Global, pp. 58-77 (link)